Question: Predictive Analytics using JMP Assignment Marketers are interested in understanding what factors determine the likelihood of attracting new customers $($predicting customer acquisition$),$ what factors determine the next best offer to make to a customer to elicit purchase $($next best offer$)$ and what factors determine customer churn $($leaving$).$ These are $3$

Predictive Analytics using JMP Assignment Marketers are interested in understanding what factors determine the likelihood of attracting new customers $($predicting customer acquisition$),$ what factors determine the next best offer to make to a customer to elicit purchase $($next best offer$)$ and what factors determine customer churn $($leaving$).$ These are $3$ situations in which marketers use predictive analytics. In this exercise we logistical regression to predict a binomial dependent variable $($for example, $1.$churn $/0.$ No churn$)$ to predict customer response. Part $1$ requires that you replicated and example from the text and par $2$ requires that you develop a model that predicts customer churn. Objective: To develop familiarity with JMP and doing predictive analytics. Part $1$: Read Chapter $5$ of Creating Better Models with JMP PRO $($pages $101$ to $114$ stop at Titanic Passengers$).$ Use the JMP PRO Application and the data table or data file: lostsales to replicate the following analysis from chapter $5.$ You are replicating the lost sales example which involves predicting order status using $3$ variables, namely quote, time to delivery and part type. The lost sales file is available in Canvas course file menu predictive analytics folder. Download the file and open it in JMP PRO. Graphs each variable individually. To save your out put use the Insert$/$clippings function in MS Word to cut and past your results into a Word document. Do the $$Fit Y by X$$ analysis using status as Y and the remaining variables as X variables. Estimate a logistic regression to predict order status $($Y$)$ using the $3$ predictor variables. The Y variable is categorical $($order$/$no order$)$ so you will select nominal logistic in the personality window. Review the parameter estimates window and identify and remove the insignificant variable $($p$<$ or$=\mathrm{.}05)$ and rerun the model. Save the output results for your report. Select fit details and report on the misclassification rate of the model. Select the red arrow at the top of the results page at Nominal Logistics Fit and scroll down to save probability formula and select. The view the data table. There are now $4$ new columns in your data. The right most columns is what the model predicts based on the data. If your compare the predictions with the actual you can identify the cases where the model makes incorrect predictions. Include a screen shot of the data table with the new results. Part $2$: Predicting Customer Churn Customer retention is a challenge in the ultracompetitive mobile phone industry. A mobile phone company is studying factors related to customer churn, a term used for customers who have moved to another service provider. The Task The company would like to build a model to predict which customers are most likely to move their service to a competitor. This knowledge will be used to identify customers for targeted interventions, with the ultimate goal of reducing churn. Use the data file Churn $2$ BBM$.$jmp in the files menu The sample data set consists of $3,332$ customer records. The response variable of interest is the column called Churn, which takes two values: True The customer has moved to another service provider. False The customer still uses $$our$$ service. The potential predictors are primarily related to service use and account. In the model specification window select true for Target Level to indicate that your model is predicting the likelihood that customers churn $($inverse of the retention rate$).$ Deliverables: Note the churn example is used in the neural network predictive modeling exercise in chapter $7.$ I don$$t require you to do the neural network model. I only required that you use the data to estimate logistic regression model predicting the likelihood of customer churn. From this exercise identify the variables that significantly predict the likelihood of a phone customer churning. Please include the results page in your report and a page view of the data table with the predicted results from step $6$ above. Note that many of the variables will be insignificant and you will need to delete them and rerun the model. Considering the variables that predict customer churn, identify $4$ bulleted $($each explained in no more than $3$ sentences$)$ recommendation to reduce phone customer churn.